arrow(c++)改写empyrical系列1---用arrow读取基金净值数据并计算夏普率
用arrow c++版本读取了csv中的基金净值数据，然后计算了夏普率，比较尴尬的是，arrow c++版本计算耗费的时间却比python的empyrical版本耗费时间多。。。
arrow新手上路，第一次自己去实现功能，实现的大概率并不是最高效的方式，但是我也踏出了用arrow c++改写backtrader的第一步。
- 用arrow改写empyrical，就当练手了，目标是做成两个文件：empyrical.h和empyrical.cpp
- 用arrow和qt改写pyfolio, 实现更美观的界面，做成两个文件：pyfolio.h 和pyfolio.cpp
- 改写backtrader
c++版本的文件：
my_example.cc
#include column = csv_table->column(i);
// std::cout << "Column " << i << ": " << column->ToString() << std::endl;
// }
// 1. 显示table信息到std::cout的方法
// std::shared_ptr record_batch;
// arrow::Result> result = csv_table->CombineChunksToBatch(); // 执行某个操作，返回Result
// if (result.ok()) {
// record_batch = result.ValueOrDie();
// // 在这里使用 record_batch
// } else {
// // 处理错误
// std::cerr << "Error: " << result.status().ToString() << std::endl;
// }
// //arrow::PrettyPrint(*record_batch, 2, &std::cout);
// arrow::Status status = arrow::PrettyPrint(*record_batch, 2, &std::cout);
// if (!status.ok()) {
// // 处理错误，例如打印错误信息
// std::cerr << "Error: " << status.ToString() << std::endl;
// }
// 2. 显示table信息到std::cout的方法
// std::cout << csv_table->ToString() << std::endl;
// 3. 显示table信息到std::cout的方法
// arrow::Status status = arrow::PrettyPrint(*csv_table, 2, &std::cout);
// if (!status.ok()) {
// // 处理错误，例如打印错误信息
// std::cerr << "Error: " << status.ToString() << std::endl;
// }
// 开始计算夏普率
// std::cout << "一年的交易日有" << AnnualizationFactors::DAILY << "天" << std::endl;
// std::cout << DAILY << std::endl;
// 计算收益率
arrow::Datum fund_returns;
arrow::Datum fund_diff;
std::shared_ptr<arrow::ChunkedArray> cum_nav = csv_table->GetColumnByName("复权净值");
std::shared_ptr<arrow::ChunkedArray> now_cum_nav = cum_nav->Slice(1,cum_nav->length()-1);
std::shared_ptr<arrow::ChunkedArray> pre_cum_nav = cum_nav->Slice(0,cum_nav->length()-1);
ARROW_ASSIGN_OR_RAISE(fund_diff, arrow::compute::CallFunction(
"subtract", {now_cum_nav,pre_cum_nav}));
ARROW_ASSIGN_OR_RAISE(fund_returns, arrow::compute::CallFunction(
"divide", {fund_diff,pre_cum_nav}));
// // 获取结果数组
// std::cout << "Datum kind: " << fund_returns.ToString()
// << " content type: " << fund_returns.type()->ToString() << std::endl;
// // std::cout << fund_returns.scalar_as().value << std::endl;
// std::cout << fund_returns.chunked_array()->ToString() << std::endl;
// 计算夏普率
arrow::Datum avg_return;
arrow::Datum avg_std;
arrow::Datum daily_sharpe_ratio;
arrow::Datum sharpe_ratio;
arrow::Datum sqrt_year;
// 创建 Arrow Double 标量
double days_of_year_double = 252.0;
std::shared_ptr<arrow::Scalar> days_of_year = arrow::MakeScalar(days_of_year_double);
ARROW_ASSIGN_OR_RAISE(sqrt_year, arrow::compute::CallFunction(
"sqrt", {days_of_year}));
ARROW_ASSIGN_OR_RAISE(avg_return, arrow::compute::CallFunction(
"mean", {fund_returns}));
arrow::compute::VarianceOptions variance_options;
variance_options.ddof = 1;
ARROW_ASSIGN_OR_RAISE(avg_std, arrow::compute::CallFunction(
"stddev", {fund_returns},&variance_options));
ARROW_ASSIGN_OR_RAISE(daily_sharpe_ratio, arrow::compute::CallFunction(
"divide", {avg_return,avg_std}));
ARROW_ASSIGN_OR_RAISE(sharpe_ratio, arrow::compute::CallFunction(
"multiply", {daily_sharpe_ratio,sqrt_year}));
std::cout << "计算得到的夏普率为 : " << sharpe_ratio.scalar_as<arrow::DoubleScalar>().value << std::endl;
auto end_time = std::chrono::high_resolution_clock::now();
auto duration = std::chrono::duration_cast<std::chrono::microseconds>(end_time - start_time);
std::cout << "c++读取数据,然后计算夏普率一共耗费时间为: " << duration.count()/1000.0 << " ms" << std::endl;
return arrow::Status::OK();
}
// (文档部分: 主函数)
int main() {
arrow::Status st = RunMain();
if (!st.ok()) {
std::cerr << st << std::endl;
return 1;
}
return 0;
}
CMakeLists.txt
cmake_minimum_required(VERSION 3.16)
project(MyExample)
find_package(Arrow REQUIRED)
find_package(Parquet REQUIRED)
find_package(ArrowDataset REQUIRED)
add_executable(my_example my_example.cc)
target_link_libraries(my_example PRIVATE Arrow::arrow_shared Parquet::parquet_shared ArrowDataset::arrow_dataset_shared)
在同一个文件夹下，运行
cmake -B build
cmake --build build
./build/my_example
python 运行代码如下：
import pandas as pd
import empyrical as ep
import time
a = time.perf_counter()
data = pd.read_csv("/home/yun/Documents/fund_nav.csv")
returns = data['复权净值'].pct_change().dropna()
sharpe_ratio = ep.sharpe_ratio(returns)
print("计算得到的sharpe_ratio : ", sharpe_ratio)
b = time.perf_counter()
print(f"python读取数据,然后计算夏普率一共耗费时间为: {(b-a)*1000.0} ms")